An Interpretable Ensemble Framework for Multi-Omics Dementia Biomarker Discovery Under HDLSS Conditions
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912585352216576 |
|---|---|
| author | Lee, Byeonghee Kang, Joonsung |
| author_facet | Lee, Byeonghee Kang, Joonsung |
| contents | Biomarker discovery in neurodegenerative diseases requires robust, interpretable frameworks capable of integrating high-dimensional multi-omics data under low-sample conditions. We propose a novel ensemble approach combining Graph Attention Networks (GAT), MultiOmics Variational AutoEncoder (MOVE), Elastic-net sparse regression, and Storey's False Discovery Rate (FDR). This framework is benchmarked against state-of-the-art methods including DIABLO, MOCAT, AMOGEL, and MOMLIN. We evaluate performance using both simulated multi-omics data and the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Our method demonstrates superior predictive accuracy, feature selection precision, and biological relevance. Biomarker gene maps derived from both datasets are visualized and interpreted, offering insights into latent molecular mechanisms underlying dementia. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_10527 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Interpretable Ensemble Framework for Multi-Omics Dementia Biomarker Discovery Under HDLSS Conditions Lee, Byeonghee Kang, Joonsung Image and Video Processing Computers and Society Machine Learning Methodology Biomarker discovery in neurodegenerative diseases requires robust, interpretable frameworks capable of integrating high-dimensional multi-omics data under low-sample conditions. We propose a novel ensemble approach combining Graph Attention Networks (GAT), MultiOmics Variational AutoEncoder (MOVE), Elastic-net sparse regression, and Storey's False Discovery Rate (FDR). This framework is benchmarked against state-of-the-art methods including DIABLO, MOCAT, AMOGEL, and MOMLIN. We evaluate performance using both simulated multi-omics data and the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Our method demonstrates superior predictive accuracy, feature selection precision, and biological relevance. Biomarker gene maps derived from both datasets are visualized and interpreted, offering insights into latent molecular mechanisms underlying dementia. |
| title | An Interpretable Ensemble Framework for Multi-Omics Dementia Biomarker Discovery Under HDLSS Conditions |
| topic | Image and Video Processing Computers and Society Machine Learning Methodology |
| url | https://arxiv.org/abs/2509.10527 |